Learning semantic ambiguities for zero-shot learning

CC BY

Saved in:
Bibliographic Details
Main Authors: Celina, Hanouti, Hervé Le, Borgne
Format: Book
Language:English
Published: Springer 2023
Subjects:
Online Access:https://link.springer.com/article/10.1007/s11042-023-14877-1
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7403
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:localhost:PNK-7403
record_format dspace
spelling oai:localhost:PNK-74032023-03-31T09:26:09Z Learning semantic ambiguities for zero-shot learning Celina, Hanouti Hervé Le, Borgne Zero-shot learning synthesize visual features CC BY Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the visual samples of seen classes and the corresponding semantic descriptions, in order to do the same on unseen classes at test time. State of the art approaches rely on generative models that synthesize visual features from the prototype of a class, such that a classifier can then be learned in a supervised manner. However, these approaches are usually biased towards seen classes whose visual instances are the only one that can be matched to a given class prototype. 2023-03-31T09:26:09Z 2023-03-31T09:26:09Z 2023 Book https://link.springer.com/article/10.1007/s11042-023-14877-1 https://dlib.phenikaa-uni.edu.vn/handle/PNK/7403 en application/pdf Springer
institution Digital Phenikaa
collection Digital Phenikaa
language English
topic Zero-shot learning
synthesize visual features
spellingShingle Zero-shot learning
synthesize visual features
Celina, Hanouti
Hervé Le, Borgne
Learning semantic ambiguities for zero-shot learning
description CC BY
format Book
author Celina, Hanouti
Hervé Le, Borgne
author_facet Celina, Hanouti
Hervé Le, Borgne
author_sort Celina, Hanouti
title Learning semantic ambiguities for zero-shot learning
title_short Learning semantic ambiguities for zero-shot learning
title_full Learning semantic ambiguities for zero-shot learning
title_fullStr Learning semantic ambiguities for zero-shot learning
title_full_unstemmed Learning semantic ambiguities for zero-shot learning
title_sort learning semantic ambiguities for zero-shot learning
publisher Springer
publishDate 2023
url https://link.springer.com/article/10.1007/s11042-023-14877-1
https://dlib.phenikaa-uni.edu.vn/handle/PNK/7403
_version_ 1761912528071294976
score 8.891053